2017-12-05 21:54:56

by Radim Krčmář

[permalink] [raw]
Subject: Re: [PATCH v2] KVM: VMX: Cache IA32_DEBUGCTL in memory

2017-11-29 01:31-0800, Wanpeng Li:
> From: Wanpeng Li <[email protected]>
>
> MSR_IA32_DEBUGCTLMSR is zeroed on VMEXIT, so it is saved/restored
> each time during world switch. Jim from Google pointed out that
> when running schbench in L2, vmx_vcpu_run will occupy 4% cpu time,
> and the 25% of vmx_vcpu_run cpu time is occupied by get_debugctlmsr().
> This patch caches the host IA32_DEBUGCTL MSR and saves/restores
> the host IA32_DEBUGCTL msr when guest/host switches to avoid to
> save/restore each time during world switch.
>
> Suggested-by: Jim Mattson <[email protected]>
> Cc: Paolo Bonzini <[email protected]>
> Cc: Radim Krčmář <[email protected]>
> Cc: Jim Mattson <[email protected]>
> Signed-off-by: Wanpeng Li <[email protected]>
> ---

Queued, thanks.

And there is another optimization loosely connected to the "[PATCH v3
00/16] Move vcpu_load and vcpu_put calls to arch code" series:
We only need to read the value for the KVM_RUN ioctl.


2017-12-06 00:15:29

by Nadav Amit

[permalink] [raw]
Subject: Re: [PATCH v2] KVM: VMX: Cache IA32_DEBUGCTL in memory

Radim Krčmář <[email protected]> wrote:

> 2017-11-29 01:31-0800, Wanpeng Li:
>> From: Wanpeng Li <[email protected]>
>>
>> MSR_IA32_DEBUGCTLMSR is zeroed on VMEXIT, so it is saved/restored
>> each time during world switch. Jim from Google pointed out that
>> when running schbench in L2, vmx_vcpu_run will occupy 4% cpu time,
>> and the 25% of vmx_vcpu_run cpu time is occupied by get_debugctlmsr().
>> This patch caches the host IA32_DEBUGCTL MSR and saves/restores
>> the host IA32_DEBUGCTL msr when guest/host switches to avoid to
>> save/restore each time during world switch.
>>
>> Suggested-by: Jim Mattson <[email protected]>
>> Cc: Paolo Bonzini <[email protected]>
>> Cc: Radim Krčmář <[email protected]>
>> Cc: Jim Mattson <[email protected]>
>> Signed-off-by: Wanpeng Li <[email protected]>
>> ---
>
> Queued, thanks.
>
> And there is another optimization loosely connected to the "[PATCH v3
> 00/16] Move vcpu_load and vcpu_put calls to arch code" series:
> We only need to read the value for the KVM_RUN ioctl.

Can you add some warning that would fire in some “debug” mode if the cached
value is not identical to the real one?

Thanks,
Nadav